Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54199
    Prev
    Next
    INDEX
    Explanations

    vegan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     인해
    -0.08
    	pop
    -0.08
     سرعة
    -0.08
     ανο
    -0.08
     بالع
    -0.08
     kurzfrist
    -0.07
     .
    -0.07
     மூலம்
    -0.07
    440
    -0.07
    552
    -0.07
    POSITIVE LOGITS
    ेको
    0.08
    /non
    0.08
    主义
    0.07
     seleccionar
    0.07
    =username
    0.07
     apoyar
    0.07
     concentrates
    0.07
     justice
    0.07
     offsetof
    0.07
    atable
    0.07
    Activations Density 0.004%

    No Known Activations